Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 1992 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.2038. Min Range: -0.2038

Max Act: 0.2038. Min Act: -0.0001

Data Index: 185524 (C4 (Web Text))

Max Activating Token Index: 736

Text #1

Max Range: 0.2038. Min Range: -0.2038

Max Act: 0.1878. Min Act: -0.0001

Data Index: 18294 (C4 (Web Text))

Max Activating Token Index: 330

Text #2

Max Range: 0.2038. Min Range: -0.2038

Max Act: 0.1935. Min Act: -0.0001

Data Index: 1101942 (C4 (Web Text))

Max Activating Token Index: 32

Text #3

Max Range: 0.2038. Min Range: -0.2038

Max Act: 0.1880. Min Act: -0.0001

Data Index: 350720 (C4 (Web Text))

Max Activating Token Index: 289

Text #4

Max Range: 0.2038. Min Range: -0.2038

Max Act: 0.1633. Min Act: -0.0001

Data Index: 268355 (C4 (Web Text))

Max Activating Token Index: 12

Text #5

Max Range: 0.2038. Min Range: -0.2038

Max Act: 0.1585. Min Act: -0.0001

Data Index: 699335 (C4 (Web Text))

Max Activating Token Index: 711

Text #6

Max Range: 0.2038. Min Range: -0.2038

Max Act: 0.1579. Min Act: -0.0001

Data Index: 783012 (C4 (Web Text))

Max Activating Token Index: 319

Text #7

Max Range: 0.2038. Min Range: -0.2038

Max Act: 0.1504. Min Act: -0.0001

Data Index: 1342410 (C4 (Web Text))

Max Activating Token Index: 103

Text #8

Max Range: 0.2038. Min Range: -0.2038

Max Act: 0.1410. Min Act: -0.0001

Data Index: 779707 (C4 (Web Text))

Max Activating Token Index: 339

Text #9

Max Range: 0.2038. Min Range: -0.2038

Max Act: 0.1456. Min Act: -0.0001

Data Index: 255445 (C4 (Web Text))

Max Activating Token Index: 741

Text #10

Max Range: 0.2038. Min Range: -0.2038

Max Act: 0.1603. Min Act: -0.0001

Data Index: 968677 (C4 (Web Text))

Max Activating Token Index: 278

Text #11

Max Range: 0.2038. Min Range: -0.2038

Max Act: 0.1492. Min Act: -0.0001

Data Index: 1045216 (C4 (Web Text))

Max Activating Token Index: 488

Text #12

Max Range: 0.2038. Min Range: -0.2038

Max Act: 0.1543. Min Act: -0.0001

Data Index: 93160 (C4 (Web Text))

Max Activating Token Index: 498

Text #13

Max Range: 0.2038. Min Range: -0.2038

Max Act: 0.1487. Min Act: -0.0001

Data Index: 786183 (C4 (Web Text))

Max Activating Token Index: 500

Text #14

Max Range: 0.2038. Min Range: -0.2038

Max Act: 0.1317. Min Act: -0.0001

Data Index: 137565 (C4 (Web Text))

Max Activating Token Index: 894

Text #15

Max Range: 0.2038. Min Range: -0.2038

Max Act: 0.1515. Min Act: -0.0001

Data Index: 946203 (C4 (Web Text))

Max Activating Token Index: 94

Text #16

Max Range: 0.2038. Min Range: -0.2038

Max Act: 0.1455. Min Act: -0.0001

Data Index: 1069517 (C4 (Web Text))

Max Activating Token Index: 225

Text #17

Max Range: 0.2038. Min Range: -0.2038

Max Act: 0.1447. Min Act: -0.0001

Data Index: 1103428 (C4 (Web Text))

Max Activating Token Index: 369

Text #18

Max Range: 0.2038. Min Range: -0.2038

Max Act: 0.1446. Min Act: -0.0001

Data Index: 215744 (C4 (Web Text))

Max Activating Token Index: 113

Text #19

Max Range: 0.2038. Min Range: -0.2038

Max Act: 0.1480. Min Act: -0.0001

Data Index: 911611 (C4 (Web Text))

Max Activating Token Index: 813